Computer vision and machine learning for defect detection in plastic containers
This solution uses computer vision and machine learning to automate defect detection in plastic containers post-blow molding. It leverages thermal and normal imaging to identify defects with enhanced contrast and image analysis, aiming to improve inspection efficiency.
Overview
The proposed solution utilizes cutting-edge computer vision and machine learning techniques to automate the detection of defects in plastic containers following the blow molding process. Traditional visual inspection is enhanced by integrating thermal and normal imaging technologies, which can identify temperature discrepancies and surface textures indicative of defects like whitish or cloudy appearances. This approach aims to improve inspection accuracy and efficiency, reducing reliance on manual checks.
Technical specifications
- Imaging Technologies: Utilizes both thermal and normal imaging to capture temperature differences and surface features.
- Preprocessing Techniques: Includes noise reduction and contrast enhancement to improve image clarity.
- Feature Extraction: Focuses on identifying key textures and heat signatures relevant to defect identification.
- Algorithm Selection: Evaluates state-of-the-art deep learning methods for image segmentation and classification.
- Iterative Model Improvement: Involves continuous refinement of machine learning models through fine-tuning and testing new algorithms.
Technology readiness level
This technology is at a TRL 5 stage, indicating that it has been validated in a relevant environment. The next steps involve further testing and refinement to move towards commercial deployment.
About University of Manitoba
The University of Manitoba is a comprehensive public research university in Winnipeg with a broad portfolio spanning discovery to translation. Industry engages through an on-campus research and technology park that colocates companies with university labs, and through a health sciences campus embedded in the city’s hospital district for clinical studies and clinical-grade prototyping. A well-established co-op and internship ecosystem and the region’s logistics hub position make collaboration, field trials, and pilot-scale testing accessible. Research is supported by competitive funding from NSERC, CIHR, SSHRC, and the Canada Foundation for Innovation. A dedicated technology transfer office provides IP strategy, licensing, and startup support with flexible agreements for corporate partners.
Inquire about this partnering listing
Industry applications
delivered to your inbox.